{"id":"34462005-f0a3-4a2c-baf7-01e638c58b4a","shortId":"J9vft6","kind":"skill","title":"recipe-implement","tagline":"Orchestrate the complete implementation lifecycle from requirements to deployment","description":"**Context**: Full-cycle implementation management (Requirements Analysis → Design → Planning → Implementation → Quality Assurance)\n\n## Orchestrator Definition\n\n**Core Identity**: \"I am an orchestrator.\" (see subagents-orchestration-guide skill)\n\n**Execution Protocol**:\n1. **Delegate all work through Agent tool** — invoke sub-agents, pass deliverable paths between them, and report results (permitted tools: see subagents-orchestration-guide \"Orchestrator's Permitted Tools\")\n2. **Follow subagents-orchestration-guide skill flows exactly**:\n   - Execute one step at a time in the defined flow (Large/Medium/Small scale)\n   - When flow specifies \"Execute document-reviewer\" → Execute it immediately\n   - **Stop at every `[Stop: ...]` marker** → Use AskUserQuestion for confirmation and wait for approval before proceeding\n3. **Enter autonomous mode** only after \"batch approval for entire implementation phase\"\n\n**CRITICAL**: Execute all steps, sub-agents, and stopping points defined in subagents-orchestration-guide skill flows.\n\n## Execution Decision Flow\n\n### 1. Current Situation Assessment\nInstruction Content: $ARGUMENTS\n\nAssess the current situation:\n\n| Situation Pattern | Decision Criteria | Next Action |\n|------------------|------------------|-------------|\n| New Requirements | No existing work, new feature/fix request | Start with requirement-analyzer |\n| Flow Continuation | Existing docs/tasks present, continuation directive | Identify next step in sub-agents.md flow |\n| Quality Errors | Error detection, test failures, build errors | Execute quality-fixer |\n| Ambiguous | Intent unclear, multiple interpretations possible | Confirm with user |\n\n### 2. Progress Verification for Continuation\n\nWhen continuing existing flow, verify:\n- Latest artifacts (PRD/ADR/Design Doc/Work Plan/Tasks)\n- Current phase position (Requirements/Design/Planning/Implementation/QA)\n- Identify next step in subagents-orchestration-guide skill corresponding flow\n\n### 3. Next Action Execution\n\n**MANDATORY subagents-orchestration-guide skill reference**:\n- Verify scale-based flow (Large/Medium/Small scale)\n- Confirm autonomous execution mode conditions\n- Recognize mandatory stopping points\n- Invoke next sub-agent defined in flow\n\n### After requirement-analyzer [Stop]\n\nWhen user responds to questions:\n- If response matches any `scopeDependencies.question` → Check `impact` for scale change\n- If scale changes → Re-execute requirement-analyzer with updated context\n- If `confidence: \"confirmed\"` or no scale change → Proceed to next step\n\n### 4. Register All Flow Steps Using TaskCreate (MANDATORY)\n\n**After scale determination, register all steps of the applicable flow using TaskCreate**:\n- First task: \"Map preloaded skills to applicable concrete rules\"\n- Register each step as individual task\n- Set currently executing step to `in_progress` using TaskUpdate\n- **Complete task registration before invoking subagents**\n\n## Subagents Orchestration Guide Compliance Execution\n\n**Pre-execution Checklist (MANDATORY)**:\n- [ ] Confirmed relevant subagents-orchestration-guide skill flow\n- [ ] Identified current progress position\n- [ ] Clarified next step\n- [ ] Recognized stopping points\n- [ ] codebase-analyzer included before Design Doc creation (Medium/Large scale)\n- [ ] code-verifier included before document-reviewer for Design Doc review (Medium/Large scale)\n- [ ] **Environment check**: Can I execute per-task commit cycle?\n  - If commit capability unavailable → Escalate before autonomous mode\n  - Other environments (tests, quality tools) → Subagents will escalate\n\n**Required Flow Compliance**:\n- Run quality-fixer before every commit\n- Obtain user approval before Edit/Write/MultiEdit outside autonomous mode\n\n### Implementation Readiness Check (between work-planner approval and task-decomposer)\n\nAfter work-planner completes and the user grants batch approval, before invoking task-decomposer, read the work plan header and find the line `Implementation Readiness: <status>`. Apply this rule:\n\n| Status | Action |\n|--------|--------|\n| `ready` | Proceed to task-decomposer |\n| `escalated` | Read the work plan's Readiness Report section, surface remaining gaps to the user via AskUserQuestion: \"Implementation Readiness is `escalated` with the following remaining gaps: [list]. Continue execution? (y/n)\". On `y` proceed; on `n` stop |\n| `pending` | Present via AskUserQuestion: \"Implementation Readiness is `pending`. Run `/recipe-prepare-implementation [plan-path]` first to verify the work plan is implementable, then resume. Continue without preflight? (y/n)\". On `y` proceed; on `n` stop |\n| absent (line missing) | Treat as `pending` — older work plans created before the readiness marker existed should be preflighted explicitly |\n\nThis check applies to all scales (Small / Medium / Large) because recipe-implement is the scale-agnostic orchestrator.\n\n## Scope Boundary for Subagents\n\nAppend the following block to every subagent prompt invoked from this recipe:\n\n```\nScope boundary for subagents:\nOperate within the task scope and referenced files in the prompt.\nUse loaded skills to execute that scope.\nEscalate when the required fix or investigation falls outside that scope.\n```\n\n## Mandatory Orchestrator Responsibilities\n\n### Task Execution Quality Cycle (4-Step Cycle per Task)\n\n**Per-task cycle** (complete each task before starting next):\n1. **Agent tool** (subagent_type: \"dev-workflows:task-executor\") → Pass task file path in prompt, receive structured response\n2. Check task-executor response:\n   - `status: escalation_needed` or `blocked` → Escalate to user\n   - `requiresTestReview` is `true` → Execute **integration-test-reviewer**\n     - `needs_revision` → Return to step 1 with `requiredFixes`\n     - `approved` → Proceed to step 3\n   - Otherwise → Proceed to step 3\n3. quality-fixer → Quality check and fixes. **Always pass** the current task file path as `task_file`\n   - `stub_detected` → Return to step 1 with `incompleteImplementations[]` details\n   - `blocked` → Escalate to user\n   - `approved` → Proceed to step 4\n4. git commit → Execute with Bash (on `approved`)\n\n### Post-Implementation Verification (After All Tasks Complete)\n\nAfter all task cycles finish, run verification agents **in parallel** before the completion report:\n\n1. **Invoke both in parallel** using Agent tool:\n   - code-verifier (subagent_type: \"dev-workflows:code-verifier\") → `doc_type: design-doc`, Design Doc path, `code_paths`: implementation file list (`git diff --name-only main...HEAD`)\n   - security-reviewer (subagent_type: \"dev-workflows:security-reviewer\") → Design Doc path, implementation file list\n\n2. **Consolidate results** — check pass/fail for each:\n   - code-verifier: **pass** when `status` is `consistent` or `mostly_consistent`. **fail** when `needs_review` or `inconsistent`. Collect `discrepancies` with status `drift`, `conflict`, or `gap`\n   - security-reviewer: **pass** when `status` is `approved` or `approved_with_notes`. **fail** when `needs_revision`. **blocked** → Escalate to user\n   - Present unified verification report to user\n\n3. **Fix cycle** (when any verifier failed):\n   - Consolidate all actionable findings into a single task file\n   - Execute task-executor with consolidated fixes → quality-fixer\n   - Re-run only the failed verifiers (by the criteria in step 2)\n   - Repeat until all pass or `blocked` → Escalate to user\n\n4. **All passed** → Proceed to Final Cleanup\n\n### Final Cleanup\n\nBefore the completion report, delete the implementation task files this recipe consumed. Their work is committed; `docs/plans/` is ephemeral working state and is not retained between recipe runs:\n\n- Delete every file matching `docs/plans/tasks/{plan-name}-task-*.md` (the `{plan-name}` derived from the work plan path used in this run)\n- Delete every file matching `docs/plans/tasks/{plan-name}-phase*-completion.md` (the per-phase completion files generated by task-decomposer)\n- Delete the corresponding `docs/plans/tasks/_overview-{plan-name}.md` if present\n- Preserve the work plan itself (`docs/plans/{plan-name}.md`) — the user decides whether to delete it after final review\n\nIf task files cannot be deleted (filesystem error), report the failure but do not block the completion report.\n\n### Test Information Communication\nAfter acceptance-test-generator execution, when invoking work-planner (subagent_type: \"dev-workflows:work-planner\"), communicate:\n- Generated integration test file path (from `generatedFiles.integration`)\n- Generated fixture-e2e test file path or null (from `generatedFiles.fixtureE2e`)\n- Generated service-integration-e2e test file path or null (from `generatedFiles.serviceE2e`)\n- Per-lane E2E absence reason (from `e2eAbsenceReason.fixtureE2e` and `e2eAbsenceReason.serviceE2e`, when each lane is null)\n- Explicit note: integration tests are created simultaneously with implementation, fixture-e2e tests are created alongside the UI feature phase, service-integration-e2e tests are executed only in the final phase\n\n## Execution Method\n\nAll work is executed through sub-agents.\nSub-agent selection follows subagents-orchestration-guide skill.","tags":["recipe","implement","claude","code","workflows","shinpr","agent-skills","agentic-ai","ai-agents","automation","claude-code","claude-code-plugin"],"capabilities":["skill","source-shinpr","skill-recipe-implement","topic-agent-skills","topic-agentic-ai","topic-ai-agents","topic-automation","topic-claude-code","topic-claude-code-plugin","topic-code-quality","topic-developer-tools","topic-development-workflow","topic-llm-orchestration","topic-productivity","topic-prompt-engineering"],"categories":["claude-code-workflows"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/shinpr/claude-code-workflows/recipe-implement","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add shinpr/claude-code-workflows","source_repo":"https://github.com/shinpr/claude-code-workflows","install_from":"skills.sh"}},"qualityScore":"0.613","qualityRationale":"deterministic score 0.61 from registry signals: · indexed on github topic:agent-skills · 327 github stars · SKILL.md body (9,125 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-02T18:53:52.735Z","embedding":null,"createdAt":"2026-04-18T22:03:13.579Z","updatedAt":"2026-05-02T18:53:52.735Z","lastSeenAt":"2026-05-02T18:53:52.735Z","tsv":"'/recipe-prepare-implementation':564 '1':42,151,697,744,780,823 '2':72,215,717,879,975 '3':118,245,751,756,757,937 '4':323,682,792,793,985 'absenc':1172 'absent':588 'accept':1120 'acceptance-test-gener':1119 'action':167,247,512,946 'agent':47,52,136,276,698,816,829,1224,1227 'agnost':624 'alongsid':1198 'alway':765 'ambigu':206 'analysi':20 'analyz':180,283,308,403 'append':630 'appli':508,609 'applic':339,349 'approv':115,125,463,476,491,747,788,800,918,920 'argument':157 'artifact':226 'askuserquest':109,535,558 'assess':154,158 'assur':25 'autonom':120,264,441,467 'base':259 'bash':798 'batch':124,490 'block':633,727,784,927,981,1111 'boundari':627,643 'build':200 'cannot':1100 'capabl':437 'chang':299,302,318 'check':295,426,471,608,718,762,882 'checklist':381 'clarifi':395 'cleanup':991,993 'code':412,832,840,850,887 'code-verifi':411,831,839,886 'codebas':402 'codebase-analyz':401 'collect':903 'commit':433,436,460,795,1009 'communic':1117,1137 'complet':6,367,485,691,808,821,996,1060,1113 'completion.md':1055 'complianc':376,453 'concret':350 'condit':267 'confid':313 'confirm':111,212,263,314,383 'conflict':908 'consist':893,896 'consolid':880,944,958 'consum':1005 'content':156 'context':13,311 'continu':182,186,219,221,546,578 'core':28 'correspond':243,1069 'creat':597,1188,1197 'creation':408 'criteria':165,972 'critic':130 'current':152,160,230,359,392,768 'cycl':16,434,681,684,690,812,939 'decid':1089 'decis':149,164 'decompos':480,496,518,1066 'defin':89,140,277 'definit':27 'deleg':43 'delet':998,1022,1046,1067,1092,1102 'deliver':54 'deploy':12 'deriv':1036 'design':21,406,420,845,847,873 'design-doc':844 'detail':783 'detect':197,776 'determin':333 'dev':703,837,868,1132 'dev-workflow':702,836,867,1131 'diff':856 'direct':187 'discrep':904 'doc':407,421,842,846,848,874 'doc/work':228 'docs/plans':1010,1082 'docs/plans/tasks':1026,1050 'docs/plans/tasks/_overview-':1070 'docs/tasks':184 'document':98,417 'document-review':97,416 'drift':907 'e2e':1148,1160,1171,1194,1206 'e2eabsencereason.fixturee2e':1175 'e2eabsencereason.servicee2e':1177 'edit/write/multiedit':465 'enter':119 'entir':127 'environ':425,444 'ephemer':1012 'error':195,196,201,1104 'escal':439,450,519,539,664,724,728,785,928,982 'everi':105,459,635,1023,1047 'exact':80 'execut':40,81,96,100,131,148,202,248,265,305,360,377,380,429,547,661,679,734,796,953,1123,1209,1215,1220 'executor':707,721,956 'exist':171,183,222,602 'explicit':606,1183 'fail':897,923,943,968 'failur':199,1107 'fall':671 'featur':1201 'feature/fix':174 'file':653,710,770,774,853,877,952,1002,1024,1048,1061,1099,1141,1150,1162 'filesystem':1103 'final':990,992,1095,1213 'find':503,947 'finish':813 'first':343,568 'fix':668,764,938,959 'fixer':205,457,760,962 'fixtur':1147,1193 'fixture-e2e':1146,1192 'flow':79,90,94,147,150,181,193,223,244,260,279,326,340,390,452 'follow':73,542,632,1229 'full':15 'full-cycl':14 'gap':530,544,910 'generat':1062,1122,1138,1145,1156 'generatedfiles.fixturee2e':1155 'generatedfiles.integration':1144 'generatedfiles.servicee2e':1167 'git':794,855 'grant':489 'guid':38,67,77,145,241,253,375,388,1233 'head':861 'header':501 'ident':29 'identifi':188,234,391 'immedi':102 'impact':296 'implement':3,7,17,23,128,469,506,536,559,575,619,803,852,876,1000,1191 'includ':404,414 'incompleteimplement':782 'inconsist':902 'individu':356 'inform':1116 'instruct':155 'integr':736,1139,1159,1185,1205 'integration-test-review':735 'intent':207 'interpret':210 'investig':670 'invok':49,272,371,493,638,824,1125 'lane':1170,1180 'larg':615 'large/medium/small':91,261 'latest':225 'lifecycl':8 'line':505,589 'list':545,854,878 'load':658 'main':860 'manag':18 'mandatori':249,269,330,382,675 'map':345 'marker':107,601 'match':292,1025,1049 'md':1031,1074,1086 'medium':614 'medium/large':409,423 'method':1216 'miss':590 'mode':121,266,442,468 'most':895 'multipl':209 'n':553,586 'name':858,1029,1035,1053,1073,1085 'name-on':857 'need':725,739,899,925 'new':168,173 'next':166,189,235,246,273,321,396,696 'note':922,1184 'null':1153,1165,1182 'obtain':461 'older':594 'one':82 'oper':646 'orchestr':4,26,33,37,66,68,76,144,240,252,374,387,625,676,1232 'otherwis':752 'outsid':466,672 'parallel':818,827 'pass':53,708,766,889,914,979,987 'pass/fail':883 'path':55,567,711,771,849,851,875,1041,1142,1151,1163 'pattern':163 'pend':555,562,593 'per':431,685,688,1058,1169 'per-lan':1168 'per-phas':1057 'per-task':430,687 'permit':61,70 'phase':129,231,1054,1059,1202,1214 'plan':22,500,523,566,573,596,1028,1034,1040,1052,1072,1080,1084 'plan-nam':1027,1033,1051,1071,1083 'plan-path':565 'plan/tasks':229 'planner':475,484,1128,1136 'point':139,271,400 'posit':232,394 'possibl':211 'post':802 'post-implement':801 'prd/adr/design':227 'pre':379 'pre-execut':378 'preflight':580,605 'preload':346 'present':185,556,931,1076 'preserv':1077 'proceed':117,319,514,551,584,748,753,789,988 'progress':216,364,393 'prompt':637,656,713 'protocol':41 'qualiti':24,194,204,446,456,680,759,761,961 'quality-fix':203,455,758,960 'question':289 're':304,964 're-execut':303 're-run':963 'read':497,520 'readi':470,507,513,525,537,560,600 'reason':1173 'receiv':714 'recip':2,618,641,1004,1020 'recipe-impl':1,617 'recogn':268,398 'refer':255 'referenc':652 'regist':324,334,352 'registr':369 'relev':384 'remain':529,543 'repeat':976 'report':59,526,822,934,997,1105,1114 'request':175 'requir':10,19,169,179,282,307,451,667 'requiredfix':746 'requirement-analyz':178,281,306 'requirements/design/planning/implementation/qa':233 'requirestestreview':731 'respond':287 'respons':291,677,716,722 'result':60,881 'resum':577 'retain':1018 'return':741,777 'review':99,418,422,738,864,872,900,913,1096 'revis':740,926 'rule':351,510 'run':454,563,814,965,1021,1045 'scale':92,258,262,298,301,317,332,410,424,612,623 'scale-agnost':622 'scale-bas':257 'scope':626,642,650,663,674 'scopedependencies.question':294 'section':527 'secur':863,871,912 'security-review':862,870,911 'see':34,63 'select':1228 'servic':1158,1204 'service-integration-e2e':1157,1203 'set':358 'simultan':1189 'singl':950 'situat':153,161,162 'skill':39,78,146,242,254,347,389,659,1234 'skill-recipe-implement' 'small':613 'source-shinpr' 'specifi':95 'start':176,695 'state':1014 'status':511,723,891,906,916 'step':83,133,190,236,322,327,336,354,361,397,683,743,750,755,779,791,974 'stop':103,106,138,270,284,399,554,587 'structur':715 'stub':775 'sub':51,135,275,1223,1226 'sub-ag':50,134,274,1222,1225 'sub-agents.md':192 'subag':36,65,75,143,239,251,372,373,386,448,629,636,645,700,834,865,1129,1231 'subagents-orchestration-guid':35,64,74,142,238,250,385,1230 'surfac':528 'task':344,357,368,432,479,495,517,649,678,686,689,693,706,709,720,769,773,807,811,951,955,1001,1030,1065,1098 'task-decompos':478,494,516,1064 'task-executor':705,719,954 'taskcreat':329,342 'taskupd':366 'test':198,445,737,1115,1121,1140,1149,1161,1186,1195,1207 'time':86 'tool':48,62,71,447,699,830 'topic-agent-skills' 'topic-agentic-ai' 'topic-ai-agents' 'topic-automation' 'topic-claude-code' 'topic-claude-code-plugin' 'topic-code-quality' 'topic-developer-tools' 'topic-development-workflow' 'topic-llm-orchestration' 'topic-productivity' 'topic-prompt-engineering' 'treat':591 'true':733 'type':701,835,843,866,1130 'ui':1200 'unavail':438 'unclear':208 'unifi':932 'updat':310 'use':108,328,341,365,657,828,1042 'user':214,286,462,488,533,730,787,930,936,984,1088 'verif':217,804,815,933 'verifi':224,256,413,570,833,841,888,942,969 'via':534,557 'wait':113 'whether':1090 'within':647 'without':579 'work':45,172,474,483,499,522,572,595,1007,1013,1039,1079,1127,1135,1218 'work-plann':473,482,1126,1134 'workflow':704,838,869,1133 'y':550,583 'y/n':548,581","prices":[{"id":"b726174d-3d2f-4e16-80b6-4999021587e6","listingId":"34462005-f0a3-4a2c-baf7-01e638c58b4a","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"shinpr","category":"claude-code-workflows","install_from":"skills.sh"},"createdAt":"2026-04-18T22:03:13.579Z"}],"sources":[{"listingId":"34462005-f0a3-4a2c-baf7-01e638c58b4a","source":"github","sourceId":"shinpr/claude-code-workflows/recipe-implement","sourceUrl":"https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-implement","isPrimary":false,"firstSeenAt":"2026-04-18T22:03:13.579Z","lastSeenAt":"2026-05-02T18:53:52.735Z"}],"details":{"listingId":"34462005-f0a3-4a2c-baf7-01e638c58b4a","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"shinpr","slug":"recipe-implement","github":{"repo":"shinpr/claude-code-workflows","stars":327,"topics":["agent-skills","agentic-ai","ai-agents","automation","claude-code","claude-code-plugin","code-quality","developer-tools","development-workflow","llm-orchestration","productivity","prompt-engineering","skills"],"license":"mit","html_url":"https://github.com/shinpr/claude-code-workflows","pushed_at":"2026-05-02T15:39:17Z","description":"Production-ready development workflows for Claude Code, powered by specialized AI agents.","skill_md_sha":"c6f0ad08383bb39f3af19d2f30c97da2f4f2c2d7","skill_md_path":"skills/recipe-implement/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-implement"},"layout":"multi","source":"github","category":"claude-code-workflows","frontmatter":{"name":"recipe-implement","description":"Orchestrate the complete implementation lifecycle from requirements to deployment"},"skills_sh_url":"https://skills.sh/shinpr/claude-code-workflows/recipe-implement"},"updatedAt":"2026-05-02T18:53:52.735Z"}}